|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: rel-cl2-lstm-3 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# rel-cl2-lstm-3 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.9812 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 3 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 3052726 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.8054 | 0.03 | 76320 | 4.7703 | |
|
|
| 4.5214 | 1.03 | 152640 | 4.4883 | |
|
|
| 4.3827 | 0.03 | 228960 | 4.3543 | |
|
|
| 4.2926 | 1.03 | 305280 | 4.2707 | |
|
|
| 4.2323 | 0.03 | 381600 | 4.2143 | |
|
|
| 4.1855 | 1.03 | 457920 | 4.1734 | |
|
|
| 4.1449 | 0.03 | 534240 | 4.1420 | |
|
|
| 4.1118 | 0.03 | 610560 | 4.1175 | |
|
|
| 4.0834 | 1.03 | 686880 | 4.0976 | |
|
|
| 4.06 | 0.03 | 763200 | 4.0817 | |
|
|
| 4.0383 | 1.03 | 839520 | 4.0689 | |
|
|
| 4.0217 | 0.03 | 915840 | 4.0581 | |
|
|
| 4.0046 | 1.03 | 992160 | 4.0483 | |
|
|
| 3.9881 | 0.03 | 1068480 | 4.0400 | |
|
|
| 3.9791 | 1.03 | 1144800 | 4.0334 | |
|
|
| 3.9628 | 0.03 | 1221120 | 4.0276 | |
|
|
| 3.9508 | 1.03 | 1297440 | 4.0224 | |
|
|
| 3.9439 | 0.03 | 1373760 | 4.0180 | |
|
|
| 3.9351 | 0.03 | 1450080 | 4.0142 | |
|
|
| 3.9291 | 1.03 | 1526400 | 4.0104 | |
|
|
| 3.9253 | 2.03 | 1602720 | 4.0073 | |
|
|
| 3.9226 | 0.03 | 1679040 | 4.0045 | |
|
|
| 3.9127 | 0.03 | 1755360 | 4.0015 | |
|
|
| 3.9077 | 1.03 | 1831680 | 3.9987 | |
|
|
| 3.8983 | 0.03 | 1908000 | 3.9967 | |
|
|
| 3.893 | 0.03 | 1984320 | 3.9944 | |
|
|
| 3.8886 | 1.03 | 2060640 | 3.9931 | |
|
|
| 3.8846 | 0.03 | 2136960 | 3.9916 | |
|
|
| 3.8799 | 0.03 | 2213280 | 3.9905 | |
|
|
| 3.8724 | 1.03 | 2289600 | 3.9890 | |
|
|
| 3.8715 | 0.03 | 2365920 | 3.9880 | |
|
|
| 3.8656 | 0.03 | 2442240 | 3.9867 | |
|
|
| 3.8601 | 1.03 | 2518560 | 3.9855 | |
|
|
| 3.8572 | 0.03 | 2594880 | 3.9846 | |
|
|
| 3.8562 | 1.03 | 2671200 | 3.9837 | |
|
|
| 3.8552 | 0.03 | 2747520 | 3.9831 | |
|
|
| 3.8573 | 1.03 | 2823840 | 3.9824 | |
|
|
| 3.8556 | 0.03 | 2900160 | 3.9819 | |
|
|
| 3.8545 | 1.03 | 2976480 | 3.9815 | |
|
|
| 3.8545 | 0.02 | 3052726 | 3.9812 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
